INDEX

Explanations

specific symbols or characters that might indicate special formatting or encoding

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dave

-0.15

 Played

-0.14

-play

-0.14

played

-0.14

 Drum

-0.14

 played

-0.14

 bookstore

-0.14

Played

-0.14

_pi

-0.14

PLAY

-0.14

POSITIVE LOGITS

 opera

0.39

 Opera

0.36

Opera

0.36

 oper

0.34

 Oper

0.31

 OPER

0.31

 Ð¾Ð¿ÐµÑĢ

0.28

 singers

0.28

 Ð¾Ð¿ÐµÑĢÐ°

0.27

Oper

0.25

Activations Density 0.006%

specific symbols or characters that might indicate special formatting or encoding

No Comments

No Known Activations